weckr-cost-estimator

weckr-cost-estimator is a skill for Claude Code from Ghiles3232/weckr-sdks. It costs 97 tokens per session (1,440 once invoked), scanned A, original, MIT.

A cost forecasting guide for AI features that use language models, such as chatbots, summarizers, and agents.

In plain words
What is it for?
Use it to forecast cost per request, user, and month; compare model choices; and check whether a feature fits a subscription price.
Why use it?
It helps estimate running costs before launch, when actual usage data is not available yet.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: positional $N argument.

Part of the weckr plugin — 4 skills, 1 MCP server shipped together

Good fit Use it to forecast cost per request, user, and month; compare model choices; and check whether a feature fits a subscription price.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ghiles3232/weckr-sdks/weckr-cost-estimator
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Ghiles3232/weckr-sdks --skill weckr-cost-estimator
Clone the repo
git clone --depth 1 https://github.com/Ghiles3232/weckr-sdks

Made for: Claude Code.

Or install weckr, the plugin that ships this one along with the rest of its 4 skills, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for weckr-cost-estimator

README.md
[![agentmods](https://agentmods.dev/badge/skills/ghiles3232/weckr-sdks/weckr-cost-estimator/github.svg)](https://agentmods.dev/skills/ghiles3232/weckr-sdks/weckr-cost-estimator)
Your own site
<a href="https://agentmods.dev/skills/ghiles3232/weckr-sdks/weckr-cost-estimator"><img src="https://agentmods.dev/badge/skills/ghiles3232/weckr-sdks/weckr-cost-estimator/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for weckr-cost-estimator

Your own site · 80×15
<a href="https://agentmods.dev/skills/ghiles3232/weckr-sdks/weckr-cost-estimator"><img src="https://agentmods.dev/badge/skills/ghiles3232/weckr-sdks/weckr-cost-estimator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,440 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00097 $0.01440
Opus 5 $0.00048 $0.00720
Sonnet 5 $0.00019 $0.00288
Haiku 4.5 $0.00010 $0.00144

Measured 12d ago against content hash 7e3f839f45ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

weckr-cost-estimator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/weckr-cost-estimator/SKILL.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Weckr cost estimator

Turn an AI feature into a cost forecast before you ship it. Given the code for an LLM call, or a plain description of the feature, estimate the tokens per call, multiply by current model prices, and project the cost per call, per active user, and per month. Then sanity check that against what the user charges.

Estimates are forecasts, not invoices. Real cost depends on real prompts, real usage, and caching. Always give a range and state the assumptions. For the exact number in production, that is what Weckr measures.

When to use this skill

Use it when the question is forward looking about a specific feature:

  • How much will this summarizer, chatbot, or agent cost to run.
  • Can I afford to offer this on a $19 plan.
  • What happens to cost if I switch from gpt-5.4 to gpt-5.4-mini, or to Claude Haiku.
  • What per user monthly spend should I expect at 500 users.

For a pure price lookup use weckr-model-pricing. For auditing profitability across a whole set of pricing plans use weckr-margin-audit. For wiring real tracking into the app use weckr-integration.

How to estimate

Work through these steps and show them, so the user can challenge any assumption.

  1. Find the call. From the code, identify the model, the system prompt, the user input, any retrieved or appended context, and the output cap (max_tokens, or a typical response length). If there is no code, ask for or assume a rough shape and say so.

  2. Estimate tokens per call. Roughly 1 token is about 4 characters of English, or about 0.75 words. Sum the system prompt, user input, and context for input tokens; use the output cap or a typical length for output tokens. If a large system prompt or context repeats across calls and the provider caches it, price those tokens at the cached-input rate.

  3. Price one call. Use current prices per million tokens (see the table below, or the weckr-model-pricing skill for the full list):

    cost_per_call = (input_tokens  / 1e6) * input_price
                  + (output_tokens / 1e6) * output_price
    

Read the full file on GitHub · 84 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 84 lines · 97 tokens per session scan A 7e3f839f45ff

Subscribe to this mod's changes

weckr-cost-estimator is a skill published in the GitHub repository Ghiles3232/weckr-sdks (8 stars, last pushed 18d ago), licensed MIT. It adds 97 tokens to every session and 1,440 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

sector-rotation

An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.

HKUDS/Vibe-Trading · 39 tokens

strategy-pivot-designer

Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.

tradermonty/claude-trading-skills · 28 tokens

twitter-reader

Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…

himself65/finance-skills · 161 tokens

chenhao-limit-up

A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.

questflowai/investorskills · 44 tokens

furusato

A Japanese hometown-tax donation manager for furusato nozei, a system where donations to municipalities can qualify for an income-tax or local-tax deduction. It reads donation receipts, stores donation records, and calculates deduction limits.

kazukinagata/shinkoku · 102 tokens

reading-receipt

An image-reading workflow for extracting structured information from receipts, invoices, and hometown-tax donation certificates. It can first extract text from PDFs and otherwise read their images.

kazukinagata/shinkoku · 64 tokens